vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [WIP] [GPT-OSS] customized symm_mem based EP comm kernel integration
- [GPUModelRunner] initialize_kv_cache cleanup (1/N): move initialization that doesn't depend on kv cache config to load_model
- [Feature] Conditional prefix logging for stdout/stderr
- [Feature] Generic Model Support via TrainableAttention and ModelRegistry parallelism constructor callback
- [Bug]: get wrong output in lm_eval test for PP mode.
- [Bug]: Batch Invariant didn't work with Qwen3-30B-A3B-Instruct-2507-AWQ
- [Core] Major fix catch backend grammar exceptions (xgrammar, outlines, etc) in scheduler
- simplify the return value from generate_beam_search
- [Optimization] Pad the number of tokens to a multiple of 4 to improve FP8 performance
- [RFC]: Replace `torch.cuda` API with `torch.accelerator` for better hardware compatiblity.
- Docs
- Python not yet supported